Using hybrid scheduling for the semi-autonomous formation of expert teams
Future Generation Computer Systems
| Hi-index | 0.00 |
In this paper, we present an innovative human agent collaboration (HAC) framework targeting flexible human agent cooperative tasks, employing multi-agent systems (MAS) technologies and human agent interaction concepts. HAC in our framework is realized through negotiated processes (e.g., negotiated task decomposition, team formation, and task allocation) involving computational agents and people, ensuring that human expert participants are kept aware and can always influence their task assignment processes through collaboration with software agents for coordinated problem solving. Among the topics we discuss are: the representation of team members' roles and capabilities, the representation of tasks and environments, potentially dynamic task decomposition, team formation and task allocation, appropriate agent architecture and MAS architecture choices, coordination among human experts and software agents through task planning, coordination communication protocols, task structure analysis for managing interdependencies among agents' tasks, and the application of these techniques to a simulated combat medical scenario.